Kimi K3 2.8T — B200 vs TPU7x Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus TPU7x (Google Ironwood) on Kimi K3 2.8T. Large-hyperscaler-volume ownership TCO normalized by total tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Near the low end of the 26–192 tok/s/user interactivity band — at 67 tok/s/user — B200 runs $0.11 per million tokens on Kimi K3 2.8T while TPU7x runs $0.05. TPU7x is the cheaper choice by 128%.
On Kimi K3 2.8T at 109 tok/s/user, the per-million math comes out to $0.18 for B200 and $0.07 for TPU7x; TPU7x delivers 171% more total tokens per dollar.
At 151 tok/s/user on Kimi K3 2.8T, B200 costs $0.29 per million tokens; TPU7x costs $0.11. TPU7x is 176% more cost-efficient at this operating point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): B200 $1.73/chip/hr · TPU7x $1.03/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B200:$0.108TPU7x:$0.048 | B200:$0.180TPU7x:$0.067 | B200:$0.293TPU7x:$0.106 |
| Concurrency | B200:~15TPU7x:~40 | B200:~7TPU7x:~23 | B200:~4TPU7x:~13 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.